A fuzzy reasoning method for handling fuzzy rules with differentspecificity levels

摘要

This paper discusses the fuzzy reasoning for fuzzy if-then ruleswith different specificity levels. The fuzzy rule-based system is amixture of general and specific fuzzy if-then rules. A general fuzzyif-then rule, which has many “don't care” conditions in theantecedent part, covers a large region of a multi-dimensional inputspace. On the other hand, a specific fuzzy if-then rule with manylinguistic conditions covers a small input region. The paper proposes afuzzy reasoning method for realizing default hierarchies of fuzzyif-then rules where specific rules have priority over general rules inthe fuzzy reasoning process. The proposed method is compared with astandard fuzzy reasoning method through computer simulations on anillustrative example